CN105354864A - Textile tissue color replacement simulation method with relatively high truth - Google Patents
Textile tissue color replacement simulation method with relatively high truth Download PDFInfo
- Publication number
- CN105354864A CN105354864A CN201510624525.7A CN201510624525A CN105354864A CN 105354864 A CN105354864 A CN 105354864A CN 201510624525 A CN201510624525 A CN 201510624525A CN 105354864 A CN105354864 A CN 105354864A
- Authority
- CN
- China
- Prior art keywords
- yarn
- fabric
- color
- binary map
- organization chart
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a textile tissue color replacement simulation method with relatively high truth. The simulation method involves a textile yarn position and region identifying and marking module and a yarn color replacement module. Through a series of novel tissue identification and color replacement algorithms, the following functions can be better realized: yarn color replacement is realized on the basis of accurate yarn position and region marking, texture features of yarns can be maintained, relatively high truth is achieved, and a tissue simulation effect after color replacement is displayed.
Description
Technical field
The present invention relates to a kind of yarn fabric tissue color replacement analogy method had compared with high realism, modeling algorithm of the present invention is mainly used in Fabric Design field.
Background technology
K mean cluster is foremost partition clustering algorithm, because succinct and efficiency make him become the most widely used in all clustering algorithms.The clusters number k of a given set of data points and needs, k is specified by user, and k mean algorithm is divided in k cluster data until meet certain end condition repeatedly according to certain distance function.
YUV a kind of colour coding method of adopting by eurovision system.In modern color television system, usual employing three pipe colour camera or colored CCD video camera carry out capture, then the colour picture signal obtained is obtained RGB after color separation, respectively amplification correction, brightness signal Y and two colour difference signal B-Y (i.e. U), R-Y (i.e. V) is obtained again through matrixer, brightness and aberration three signals are encoded by last transmitting terminal respectively, send with same channel.The method for expressing of this color is exactly that so-called YUV color space represents.The importance of YUV color space is adopted to be that its brightness signal Y is separated with carrier chrominance signal U, V.
Along with the theoretical research of clustering algorithm and deepening continuously and developing of applied research, it is applied to each engineering field by people gradually, achieves huge success.In Fabric Design field, clustering algorithm is usually used to pair warp and weft yarn and classifies, to realize the precise positioning of yarn.The yarn positioning result utilizing cluster to obtain, by the channel value of YUV color space replace just can realize reservation cloth textured while carry out yarn color replacement, the color matching design process of fabric can be realized easily.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, provide a kind of yarn fabric tissue color replacement analogy method had compared with high realism.
Technical scheme of the present invention is as follows:
A kind of have compared with high realism yarn fabric tissue color replace analogy method comprise the steps:
1) yarn region recognition and mark
Identify in yarn fabric scan image and mark position, the region of different yarns;
2) stitch yarn color is replaced
While carrying out yarn color replacement, retain textural characteristics, there is the higher sense of reality.
Further, described step 1) be specially:
1.1 pairs of yarn fabric scan images and fabric organization chart carry out gaussian filtering, smothing filtering;
1.2 utilize clustering algorithm to classify to filtered image according to yarn color difference, generate preliminary fabric binary map;
1.3 utilize connected domain area algorithm to remove high bright spot impact in preliminary fabric binary map, obtain accurate fabric binary map, realize yarn position, the identification in region and mark.
Further, described step 1.3 is specially:
Using the setting ratio of the average area of all connected domains of white tissues point in preliminary fabric binary map as threshold value, removing the white connected domain that all areas are less than this threshold value, is black by pixel assignment all in these white connected domains; In like manner, using the same setting ratio of the average area of all connected domains of dark structure point in preliminary fabric binary map as threshold value, remove the black connected domain that all areas are less than this threshold value, be white by pixel assignment all in these black connected domains, obtain accurate fabric binary map.
Further, described step 2) be specially:
2.1 according to step 1) obtain fabric binary map accurately, determine all pixel positions of often kind of yarn, create one with the blank sheet of the equal size of fabric organization chart, by the rgb value that the rgb value assignment of all pixel positions of often kind of yarn in blank sheet is selected color of object, obtain the organization chart after all yarn colour changings thus, this figure only has fabric color information, does not have texture information;
2.2 characteristics be separated with carrier chrominance signal U, V according to the brightness signal Y of YUV color space, to needing the yarn of colour changing to replace, retain the textural characteristics of yarn simultaneously;
Be yuv space by the organization chart after fabric organization chart and yarn colour changing by RGB color space conversion, the carrier chrominance signal U of pixel each in the organization chart after yarn colour changing, V channel value are all replaced with carrier chrominance signal U, the V value of correspondence position pixel in fabric organization chart, obtain texture information thus.
Further, described clustering algorithm is K means clustering algorithm.
Analogy method of the present invention comprises fabric yarn position, region recognition and mark module, Yarn color replacement module.By tissue identification, the color replacement of series of new, can following functions preferably: the replacement realizing Yarn color on the basis to yarn position, region accurate marker, the textural characteristics of yarn can be retained simultaneously, there is the higher sense of reality, demonstrate the microstructure modeling effect after colour changing.
Accompanying drawing explanation
Fig. 1 be different yarns and interlacing point region identification and mark design sketch, (a) for identify and mark before, (b) for identify and mark after;
Fig. 2 is the simulate effect figure that different yarns carries out color replacement, and (a) is organizer figure, and (b) is the corresponding binary map of interlacing point yellow in tissue; C () is the corresponding binary map of interlacing point red in tissue; D () is the corresponding binary map of white tissues point in tissue; E () is the design sketch after colour changing;
Fig. 3 is the sample comparison diagram whether retaining grain effect after yarn colour changing, and (a) is the organization chart not retaining texture, and (b) is the organization chart retaining texture.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Although describe the present invention in conjunction with specific embodiment here, some change and amendment is apparent for a person skilled in the art, and it does not depart from true spirit of the present invention.Therefore, the present invention is understood by specific descriptions here, but is understood by claims.
A kind of have compared with high realism yarn fabric tissue color replace analogy method comprise the steps:
1) yarn region recognition and mark
Identify in yarn fabric scan image and mark position, the region of different yarns;
2) stitch yarn color is replaced
While carrying out yarn color replacement, retain textural characteristics, there is the higher sense of reality.
Further, described step 1) be specially:
1.1 pairs of yarn fabric scan images and fabric organization chart carry out gaussian filtering, smothing filtering;
1.2 utilize clustering algorithm to classify to filtered image according to yarn color difference, generate preliminary fabric binary map;
1.3 utilize connected domain area algorithm to remove high bright spot impact in preliminary fabric binary map, obtain accurate fabric binary map, realize yarn position, the identification in region and mark.
Further, described step 1.3 is specially:
Using the setting ratio of the average area of all connected domains of white tissues point in preliminary fabric binary map as threshold value, removing the white connected domain that all areas are less than this threshold value, is black by pixel assignment all in these white connected domains; In like manner, using the same setting ratio of the average area of all connected domains of dark structure point in preliminary fabric binary map as threshold value, remove the black connected domain that all areas are less than this threshold value, be white by pixel assignment all in these black connected domains, obtain accurate fabric binary map.
Further, described step 2) be specially:
2.1 according to step 1) obtain fabric binary map accurately, determine all pixel positions of often kind of yarn, create one with the blank sheet of the equal size of fabric organization chart, by the rgb value that the rgb value assignment of all pixel positions of often kind of yarn in blank sheet is selected color of object, obtain the organization chart after all yarn colour changings thus, this figure only has fabric color information, does not have texture information;
2.2 characteristics be separated with carrier chrominance signal U, V according to the brightness signal Y of YUV color space, to needing the yarn of colour changing to replace, retain the textural characteristics of yarn simultaneously;
Be yuv space by the organization chart after fabric organization chart and yarn colour changing by RGB color space conversion, the carrier chrominance signal U of pixel each in the organization chart after yarn colour changing, V channel value are all replaced with carrier chrominance signal U, the V value of correspondence position pixel in fabric organization chart, obtain texture information thus.
Further, described clustering algorithm is K means clustering algorithm.
Fig. 1 illustrates the effect adopting analogy method of the present invention fabric structure figure to be carried out to yarn position, region recognition, mark.Utilize the feature that the proterties such as different yarns color, texture, brightness in fabric tissue all there are differences, after man-machine interaction setting cluster color number, adopt K means clustering algorithm tentatively to obtain yarn zone marker figure.The situation such as highlighted interference, yarn obscurity boundary that the overexposure that may exist in for scanning process causes, introduce Morphological scale-space method, i.e. dilation erosion, revises error, thus obtains yarn regional distribution chart (binary map) comparatively accurately.
Fig. 2 illustrates on the basis that marked yarn distributed areas, different yarns is carried out to the simulate effect of color replacement.In the process, introduce color space conversion method, utilize Y (brightness) and U, V (colourity) signal in YUV model separate, and Y-channel represents fabric texture information, U, V represent the characteristic of fabric color information, be transformed into yuv space after yarn zone marker figure is given colour changing, and the Y channel signal of this figure is replaced with the Y channel signal of source textile image, finally convert back RGB color space and obtain final colour changing design sketch.Utilizing this kind of novel colour changing method, realizing the textural characteristics retaining source textile while Yarn color is replaced preferably, good simulate effect can be obtained.Whether retain the weak effect distance comparison diagram that texture brings after Fig. 3 illustrates colour changing, fully demonstrate the superiority of this method.
Set forth the present invention by above-mentioned example, other example also can be adopted to realize the present invention, the present invention is not limited to above-mentioned instantiation, and therefore the present invention is limited by claims scope simultaneously.
Claims (5)
1. have and replace an analogy method compared with the yarn fabric tissue color of high realism, it is characterized in that comprising the steps:
1) yarn region recognition and mark
Identify in yarn fabric scan image and mark position, the region of different yarns;
2) stitch yarn color is replaced
While carrying out yarn color replacement, retain textural characteristics, there is the higher sense of reality.
2. have as claimed in claim 1 and replace analogy method compared with the yarn fabric tissue color of high realism, it is characterized in that described step 1) be specially:
1.1 pairs of yarn fabric scan images and fabric organization chart carry out gaussian filtering, smothing filtering;
1.2 utilize clustering algorithm to classify to filtered image according to yarn color difference, generate preliminary fabric binary map;
1.3 utilize connected domain area algorithm to remove high bright spot impact in preliminary fabric binary map, obtain accurate fabric binary map, realize yarn position, the identification in region and mark.
3. have as claimed in claim 2 and replace analogy method compared with the yarn fabric tissue color of high realism, it is characterized in that described step 1.3 is specially:
Using the setting ratio of the average area of all connected domains of white tissues point in preliminary fabric binary map as threshold value, removing the white connected domain that all areas are less than this threshold value, is black by pixel assignment all in these white connected domains; In like manner, using the same setting ratio of the average area of all connected domains of dark structure point in preliminary fabric binary map as threshold value, remove the black connected domain that all areas are less than this threshold value, be white by pixel assignment all in these black connected domains, obtain accurate fabric binary map.
4. have as claimed in claim 1 and replace analogy method compared with the yarn fabric tissue color of high realism, it is characterized in that described step 2) be specially:
2.1 according to step 1) obtain fabric binary map accurately, determine all pixel positions of often kind of yarn, create one with the blank sheet of the equal size of fabric organization chart, by the rgb value that the rgb value assignment of all pixel positions of often kind of yarn in blank sheet is selected color of object, obtain the organization chart after all yarn colour changings thus, this figure only has fabric color information, does not have texture information;
2.2 characteristics be separated with carrier chrominance signal U, V according to the brightness signal Y of YUV color space, to needing the yarn of colour changing to replace, retain the textural characteristics of yarn simultaneously;
Be yuv space by the organization chart after fabric organization chart and yarn colour changing by RGB color space conversion, the carrier chrominance signal U of pixel each in the organization chart after yarn colour changing, V channel value are all replaced with carrier chrominance signal U, the V value of correspondence position pixel in fabric organization chart, obtain texture information thus.
5. have as claimed in claim 2 and replace analogy method compared with the yarn fabric tissue color of high realism, it is characterized in that described clustering algorithm is K means clustering algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510624525.7A CN105354864A (en) | 2015-09-25 | 2015-09-25 | Textile tissue color replacement simulation method with relatively high truth |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510624525.7A CN105354864A (en) | 2015-09-25 | 2015-09-25 | Textile tissue color replacement simulation method with relatively high truth |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105354864A true CN105354864A (en) | 2016-02-24 |
Family
ID=55330831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510624525.7A Pending CN105354864A (en) | 2015-09-25 | 2015-09-25 | Textile tissue color replacement simulation method with relatively high truth |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354864A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105803623A (en) * | 2016-04-18 | 2016-07-27 | 南京航空航天大学 | Computer pattern recognition method for composite material microstructure |
| CN105844675A (en) * | 2016-03-24 | 2016-08-10 | 上海工程技术大学 | Color cluster analysis method of yarn-dyed fabric |
| CN105844676A (en) * | 2016-03-24 | 2016-08-10 | 上海工程技术大学 | Color cluster analysis device and color cluster analysis method for printed fabric |
| CN106485288A (en) * | 2016-12-21 | 2017-03-08 | 上海工程技术大学 | A kind of automatic identifying method of yarn dyed fabric tissue |
| CN108647687A (en) * | 2018-04-23 | 2018-10-12 | 浙江大学 | A kind of fabric tissue recognition methods based on translation subtractive method |
| CN109636871A (en) * | 2018-12-07 | 2019-04-16 | 北京金山云网络技术有限公司 | Transform method, device and the terminal device of picture color |
| CN115797260A (en) * | 2022-11-03 | 2023-03-14 | 武汉纺织大学 | Visual high-fidelity textile fabric color changing method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629386A (en) * | 2012-03-28 | 2012-08-08 | 浙江大学 | Region segmentation method for colorful textile texture images |
| CN102980659A (en) * | 2012-11-07 | 2013-03-20 | 上海工程技术大学 | Digitalized characterization method of monochrome tight fabric surface color |
-
2015
- 2015-09-25 CN CN201510624525.7A patent/CN105354864A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629386A (en) * | 2012-03-28 | 2012-08-08 | 浙江大学 | Region segmentation method for colorful textile texture images |
| CN102980659A (en) * | 2012-11-07 | 2013-03-20 | 上海工程技术大学 | Digitalized characterization method of monochrome tight fabric surface color |
Non-Patent Citations (2)
| Title |
|---|
| 孙佳理: "基于数字图像处理的纺织物辅助设计模拟系统开发", 《轻工机械》 * |
| 杨娜 等: "基于图像处理技术的织物组织自动识别", 《山东纺织科技》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844675A (en) * | 2016-03-24 | 2016-08-10 | 上海工程技术大学 | Color cluster analysis method of yarn-dyed fabric |
| CN105844676A (en) * | 2016-03-24 | 2016-08-10 | 上海工程技术大学 | Color cluster analysis device and color cluster analysis method for printed fabric |
| CN105803623A (en) * | 2016-04-18 | 2016-07-27 | 南京航空航天大学 | Computer pattern recognition method for composite material microstructure |
| CN105803623B (en) * | 2016-04-18 | 2017-08-04 | 南京航空航天大学 | A kind of computer graphical recognition methods of composite microscopical structure |
| CN106485288A (en) * | 2016-12-21 | 2017-03-08 | 上海工程技术大学 | A kind of automatic identifying method of yarn dyed fabric tissue |
| CN106485288B (en) * | 2016-12-21 | 2023-11-28 | 上海工程技术大学 | Automatic identification method for colored fabric tissue |
| CN108647687A (en) * | 2018-04-23 | 2018-10-12 | 浙江大学 | A kind of fabric tissue recognition methods based on translation subtractive method |
| CN108647687B (en) * | 2018-04-23 | 2021-09-24 | 浙江大学 | Fabric tissue identification method based on translation subtraction method |
| CN109636871A (en) * | 2018-12-07 | 2019-04-16 | 北京金山云网络技术有限公司 | Transform method, device and the terminal device of picture color |
| CN115797260A (en) * | 2022-11-03 | 2023-03-14 | 武汉纺织大学 | Visual high-fidelity textile fabric color changing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105354864A (en) | Textile tissue color replacement simulation method with relatively high truth | |
| CN106780438B (en) | Insulator defect detection method and system based on image processing | |
| CN103093203B (en) | A kind of human body recognition methods again and human body identify system again | |
| CN104408424B (en) | A kind of multi signal lamp recognition methods based on image procossing | |
| CN106485199A (en) | A kind of method and device of body color identification | |
| JP2005229620A (en) | System and method for generating high compression image data file having multiple foreground planes | |
| KR20210006276A (en) | Image processing method for flicker mitigation | |
| CN103400121A (en) | License plate locating method based on colorful binary image | |
| CN105812674A (en) | Signal lamp color correction method, monitoring method, and device thereof | |
| CN104021544B (en) | A kind of greenhouse vegetable disease monitor video extraction method of key frame, that is, extraction system | |
| CN104778833A (en) | Traffic light recognition method | |
| CN103824078B (en) | The many license plate locating methods of complex scene | |
| CN111223108A (en) | Method and system based on backdrop matting and fusion | |
| CN110428439A (en) | A kind of shadow detection method based on shadow region color saturation property | |
| CN107481183A (en) | A kind of twilight image colorization method based on multi-dimensional association rule | |
| CN105578080A (en) | Imaging method, image sensor, imaging device and electronic device | |
| CN103164847A (en) | Method for eliminating shadow of moving target in video image | |
| CN105578081A (en) | Imaging method, image sensor, imaging device and electronic device | |
| Du et al. | Double-channel guided generative adversarial network for image colorization | |
| CN104574377A (en) | Method for correcting yellow cast of red lamp of electronic police | |
| CN109472767B (en) | Stage lamp missing state analysis system | |
| CN110188640B (en) | Face recognition method, face recognition device, server and computer readable medium | |
| CN103034997B (en) | Foreground detection method for separation of foreground and background of surveillance video | |
| CN109800693B (en) | Night vehicle detection method based on color channel mixing characteristics | |
| Shiting et al. | Clustering-based shadow edge detection in a single color image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160224 |